Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 59 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5498. Min Range: -7.5498
Max Act: 7.5498. Min Act: -0.1700
Data Index: 8009327 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5498. Min Range: -7.5498
Max Act: 7.4560. Min Act: -0.1700
Data Index: 3195555 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5498. Min Range: -7.5498
Max Act: 7.2373. Min Act: -0.1700
Data Index: 3860723 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5498. Min Range: -7.5498
Max Act: 7.2060. Min Act: -0.1700
Data Index: 4157373 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5498. Min Range: -7.5498
Max Act: 7.1435. Min Act: -0.1700
Data Index: 1395649 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5498. Min Range: -7.5498
Max Act: 7.0810. Min Act: -0.1700
Data Index: 7591169 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5498. Min Range: -7.5498
Max Act: 7.0810. Min Act: -0.1700
Data Index: 1609565 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5498. Min Range: -7.5498
Max Act: 7.0810. Min Act: -0.1700
Data Index: 2905326 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5498. Min Range: -7.5498
Max Act: 7.0185. Min Act: -0.1700
Data Index: 8230580 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5498. Min Range: -7.5498
Max Act: 7.0498. Min Act: -0.1700
Data Index: 5200018 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5498. Min Range: -7.5498
Max Act: 7.0185. Min Act: -0.1700
Data Index: 1202058 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5498. Min Range: -7.5498
Max Act: 7.0185. Min Act: -0.1700
Data Index: 4728190 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5498. Min Range: -7.5498
Max Act: 7.0185. Min Act: -0.1700
Data Index: 907857 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5498. Min Range: -7.5498
Max Act: 6.9873. Min Act: -0.1700
Data Index: 7763807 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5498. Min Range: -7.5498
Max Act: 6.9873. Min Act: -0.1700
Data Index: 5330800 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5498. Min Range: -7.5498
Max Act: 6.9873. Min Act: -0.1700
Data Index: 1353460 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5498. Min Range: -7.5498
Max Act: 6.9560. Min Act: -0.1700
Data Index: 4699980 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5498. Min Range: -7.5498
Max Act: 6.9248. Min Act: -0.1700
Data Index: 791138 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5498. Min Range: -7.5498
Max Act: 6.9248. Min Act: -0.1700
Data Index: 2432094 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5498. Min Range: -7.5498
Max Act: 6.9248. Min Act: -0.1700
Data Index: 1553597 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #19